Loading the SOTA2 catalog…
SOTA2 Research · benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
| Task | Dataset | Domain | Trend | Results | Last Update |
|---|---|---|---|---|---|
| Time-series Forecasting | Flu-US | 36 | Feb 26, 2026 | ||
| Composed Image Retrieval | CIRCO 1.0 (test) | 36 | Feb 26, 2026 | ||
| Scene Text Recognition | WordArt | 36 | Jun 24, 2026 | ||
| Scientific Reasoning | CEval Hard | 36 | May 19, 2026 | ||
| Text Reconstruction Attack | Rotten Tomatoes | 36 | Feb 26, 2026 | ||
| Text Reconstruction Attack |
| SST-2 |
| 36 |
| Feb 26, 2026 |
| Text Reconstruction Attack | CoLA | 36 | Feb 26, 2026 |
|---|
| Image Classification | CIFAR-100 | 36 | Feb 26, 2026 |
|---|
| Unsupervised Accuracy Estimation | RR1-WILDS | 36 | Feb 26, 2026 |
|---|
| Unsupervised Accuracy Estimation | DomainNet | 36 | Feb 26, 2026 |
|---|
| Unsupervised Accuracy Estimation | Office-Home | 36 | Feb 26, 2026 |
|---|
| Accuracy Estimation | Nonliving-26 Subpopulation Shift | 36 | Feb 26, 2026 |
|---|
| Accuracy Estimation | Living-17 Subpopulation Shift | 36 | Feb 26, 2026 |
|---|
| Accuracy Estimation | Entity-30 Subpopulation Shift | 36 | Feb 26, 2026 |
|---|
| Accuracy Estimation | Entity-13 Subpopulation Shift | 36 | Feb 26, 2026 |
|---|
| Graph Anomaly Detection | MUTAG | 36 | May 27, 2026 |
|---|
| Emotion Recognition | IEMOCAP (test) | 36 | Feb 26, 2026 |
|---|
| Classification | stock | 36 | Feb 26, 2026 |
|---|
| Tabular Data Synthesis | stock | 36 | Feb 26, 2026 |
|---|
| Tabular Data Synthesis Fidelity | stock | 36 | Feb 26, 2026 |
|---|
| Camera Pose Estimation | CO3D v2 (evaluation sequences) | 36 | Feb 26, 2026 |
|---|
| Denoising | BSD68 sigma=50 (test) | 36 | Mar 31, 2026 |
|---|
| Link Prediction | ca-GrQc | 36 | May 13, 2026 |
|---|
| Image Classification | CIFAR-100 l=50000 (test) | 36 | Feb 26, 2026 |
|---|
| Image Classification | CIFAR-10 l=50000 (test) | 36 | Feb 26, 2026 |
|---|